Plugins

Bioinformatics agent preset with 17 BioDSH analysis skills (single-cell, bulk RNA-seq, survival, regression, ANOVA), a 2000+ skill library searched by a skill_library tool, per-message skill selection and a time/step convergence guard.

QA pipeline as 10 agent skills: requirement analysis, test strategy, case writing and review, E2E (Playwright) and API automation, exploratory, regression scope and bug analysis, backed by a shared knowledge base with format rules, risk model and schema validators.

Drive OriginLab Origin scientific plotting from AI chat via MCP: 62 tools. Modal-dialog watchdog, LabTalk safety gate, release/reconnect, fit with initial/fixed/weighted params, fine-grained plot and sheet edits, matrix tools, FigureSpec declarative YAML (diff-able and replayable), MCP Resources read-only snapshot, matplotlib-figure bridge, PowerPoint assembly with panel labels, Graph Gallery template search, EPS export, file-access whitelist, visual regression baseline, and editable OPJU delivery with deterministic readback verification.

Design-fidelity QA for text-only models: a `deepseek_vision` tool borrows an eye from any OpenAI-compatible vision route, so the model can judge whether an implementation matches its mock — shipped with the benchmark behind that judgement (four fixtures, 23 injected defects, raw transcripts) and the questioning discipline it depends on.

Mobile web shell for the DSH Web GUI: overlay drawers, draggable FAB, mobile composer fixes, and a floating image-upload button pinned above the composer (native gallery/camera, integrated with the validated add-images pipeline), zero desktop regression. Published on npm as dsh-webui-mobile.

Evaluation harness for DSH plugins: YAML cases drive real headless agent runs, assert on tool calls, args, results and token usage, with a baseline gate for CI regression.

Claim-verification skill that checks design documents and plans against codebase facts, escalating behavioral claims to executable logic-primitive verification for state machines and data models, with before/after regression, domain constraints, and concurrency risk mining.

A self-evolving plugin for DeepSeek Harness: it observes how the agent runs, proposes improvements to its own assets via the LLM, validates each proposal inside a sandboxed trial agent, and applies only verified mutations — with a versioned ledger and automatic rollback on regression.

Behavior-drift reports for DSH sessions: compares two session logs and reports tool-sequence alignment, tool mix, reasoning volume, timing, retries and file targets, with an optional CI threshold gate. Zero dependencies.

Run Stata through DeepSeek Harness: the native Stata AI Skill service auto-starts with DSH (macOS/Windows binaries bundled), so you can run regressions, do-files and econometrics workflows with no manual setup.

Frontend GUI debugging and testing for DeepSeekHarness agents: 36 browser_* tools for structured GUI automation, visual comparison, dynamic frame analysis and network debugging on Web/Chromium.

Circuit breaker for idle agent turns: watches agent/assistant-stream and cancels a turn that produces only reasoning — no text and no tool call — after 45s, after 80000 reasoning characters, or on a degenerate repetition pattern (exact repeat unit, sentence-template repeat, sparse repeat, or 6-gram density). On trip it injects a continue instruction that requires the next action to be a tool call, and ships 11 regression cases plus per-gate tuning.

dsh-lint-loop v0.7.0 adds bounded, read-only evidence checks for observable shell/bash/pwsh and file-tool changes; uncertain evidence remains incomplete. [Release](https://github.com/lemonxiny55/dsh-lint-loop/releases/tag/v0.7.0).

Mobile adapter for the DSH web shell: overlay sidebar/details drawers, responsive composer and settings below 768px, zero desktop regression.

QA orchestrator plugin for DeepSeek Harness: an agent explores your app and leaves evidence, then the explored path replays deterministically. Drives the browser, macOS desktop, iOS and Android drivers.

Adds a /dshpp slash command that reports session and token usage, cache-hit rate, and estimated cost from harness session logs; the repo also ships a CLI and local web console for lifecycle, provider, session, and plugin-security management.

Decision-and-goal memory with lineage: explicit commands and a model tool record decisions deterministically, a status card re-anchors them across compaction, a lossless event stream with BM25+jieba retrieval backs it, and a scenario-level fidelity regression suite gates releases.

Run Stata through DeepSeek Harness: the native Stata AI Skill service auto-starts with DSH (macOS/Windows binaries bundled), so you can run regressions, do-files and econometrics workflows with no manual setup.

Independent browser acceptance testing for agent deliverables: JSON spec in, real-Chromium verdict out.

Records browser bugs, freezes expected results, and verifies fixes against a fresh original-code control.

Contract regression harness for plugin authors: a scripted LLM adapter drives the real pipeline in isolated child processes with session-event assertions (load/contract/behavior/fault layers); zero API key, CI-ready.

Merges your configured, runtime-registered and locally cached models into one panel, probes and minimal-request tests them, pulls each channel's upstream /v1/models catalog, and chains the keepers into named schemes. A virtual ModelPool provider fails over at request time with per-model cooldowns, exponential backoff, image-request avoidance for text-only models, and a 10-minute memory for rejected reasoning levels. Adds a token ledger by day and model with CSV export, and 21 regression probes. Not a fork of dsh-llm-fallbacks.

Records a session as a run, replays it in an isolated workspace copy with another model or prompt, diffs the two trajectories side by side, aggregates runs into a task × variant matrix, and gates regressions with task assertions and a CI exit code.

Agent application development evaluation skill (skill bundle) for DeepSeek Harness: offline/online suites judged from audit side effects, baseline diff with zero tolerance for safety regressions, and mutation tests proving the evaluators themselves catch regressions. Framework-agnostic - needs a callable chat endpoint and queryable tool-call records. DSH host compatibility is deliberately undeclared.